A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks.
The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-11-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1011597 |
| _version_ | 1797435727730966528 |
|---|---|
| author | Shuting Jin Yue Hong Li Zeng Yinghui Jiang Yuan Lin Leyi Wei Zhuohang Yu Xiangxiang Zeng Xiangrong Liu |
| author_facet | Shuting Jin Yue Hong Li Zeng Yinghui Jiang Yuan Lin Leyi Wei Zhuohang Yu Xiangxiang Zeng Xiangrong Liu |
| author_sort | Shuting Jin |
| collection | DOAJ |
| description | The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks. |
| first_indexed | 2024-03-09T10:52:25Z |
| format | Article |
| id | doaj.art-6ed5ac3111744e7fa1514fee54e1c1fc |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-03-09T10:52:25Z |
| publishDate | 2023-11-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-6ed5ac3111744e7fa1514fee54e1c1fc2023-12-01T05:30:54ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582023-11-011911e101159710.1371/journal.pcbi.1011597A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks.Shuting JinYue HongLi ZengYinghui JiangYuan LinLeyi WeiZhuohang YuXiangxiang ZengXiangrong LiuThe powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks.https://doi.org/10.1371/journal.pcbi.1011597 |
| spellingShingle | Shuting Jin Yue Hong Li Zeng Yinghui Jiang Yuan Lin Leyi Wei Zhuohang Yu Xiangxiang Zeng Xiangrong Liu A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. PLoS Computational Biology |
| title | A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. |
| title_full | A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. |
| title_fullStr | A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. |
| title_full_unstemmed | A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. |
| title_short | A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. |
| title_sort | general hypergraph learning algorithm for drug multi task predictions in micro to macro biomedical networks |
| url | https://doi.org/10.1371/journal.pcbi.1011597 |
| work_keys_str_mv | AT shutingjin ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yuehong ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT lizeng ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yinghuijiang ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yuanlin ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT leyiwei ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT zhuohangyu ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT xiangxiangzeng ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT xiangrongliu ageneralhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT shutingjin generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yuehong generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT lizeng generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yinghuijiang generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT yuanlin generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT leyiwei generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT zhuohangyu generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT xiangxiangzeng generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks AT xiangrongliu generalhypergraphlearningalgorithmfordrugmultitaskpredictionsinmicrotomacrobiomedicalnetworks |